Quantitative analysis of brain white matter lesions in multiple sclerosis subjects

• Published in: IEEE journal of biomedical and health informatics pp. 1 - 4
• Main Authors: Loizou, C.P., Pattichis, C.S., Seimenis, I., Pantziaris, M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2009
• Subjects: Diseases; Image analysis; Image segmentation; Image texture analysis; Lesions; Magnetic analysis; Magnetic resonance; Magnetic resonance imaging; MRI; Multiple sclerosis; Shape; shape features; texture analysis
• ISSN: 2168-2194
• DOI: 10.1109/ITAB.2009.5394340

In this study the value of magnetic resonance image (MRI) shape and texture analysis was assessed in multiple sclerosis (MS) subjects, both in differentiating between normal or normal appearing and abnormal tissue and in assessing disease onset. Shape and texture analysis was carried out in normal brain white matter and lesions detected in transverse sections of T2-weighted magnetic resonance (MR) images acquired from 22 symptomatic untreated subjects. All detected brain lesions were manually segmented by an experienced MS neurologist and confirmed by a radiologist. The results showed that there was no significant difference for most of the shape features and for all of the texture features between MS lesions at 0 and 6-12 months. For some texture features there was significant difference between normal or normal appearing tissue and MS lesions at 0 and 6-12 months. Further research with more subjects is required for computing shape and texture features that may provide information for better and earlier differentiation between normal tissue and MS lesions.